https://github.com/joshcap20/nflpredictor
ML predictions for football
https://github.com/joshcap20/nflpredictor
football machine-learning
Last synced: 5 months ago
JSON representation
ML predictions for football
- Host: GitHub
- URL: https://github.com/joshcap20/nflpredictor
- Owner: JoshCap20
- Created: 2024-09-16T05:37:07.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-16T06:25:54.000Z (over 1 year ago)
- Last Synced: 2025-02-24T03:22:53.826Z (over 1 year ago)
- Topics: football, machine-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 400 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ML for NFL Game Winner Predictions
Simple project adapted from various sources to predict the winner of NFL games using machine learning. This is a combination of Python scripts and Juypter notebooks.
## Using the Model
Make sure to install the requirements by running `pip install -r requirements.txt` in the Python environment you are using.
To first generate the model, run the `train.ipynb` notebook. This will generate a `clf.pkl` file that will be used later to predict the winner of games. Running this notebook may take a few minutes as it acquires the necessary data and trains the models.
Then, you can run the `predict.ipynb` notebook to predict the winner of games for a given week. This will then analyze betting lines and determine if there is a good bet to make.
`data.py` provides utilities for externally acquiring the data needed for the model, and `weekly_predictions.py` provides utilities for predicting the winner of games for a given week.